mlsanityData to 7 Oct 2026

PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding

arXiv 2107.10466 ↗First posted 22 Jul 2021cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additional computation and a waste of time. This paper, however, presents a novel framework PoseDet (Estimating Pose by Detection) to localize and associate body joints simultaneously at higher inference speed. Moreover, we propose the keypoint-aware pose embedding to represent an object in terms of the locations of its keypoints. The proposed pose embedding contains semantic and geometric information, allowing us to access discriminative and informative features efficiently. It is utilized for candidate classification and body joint localization in PoseDet, leading to robust predictions of various poses. This simple framework achieves an unprecedented speed and a competitive accuracy on the COCO benchmark compared with state-of-the-art methods. Extensive experiments on the CrowdPose benchmark show the robustness in the crowd scenes. Source code is available.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 32 of its 47 references that are in the map. First posted on arXiv 22 Jul 2021.

Builds on

32 of 47 references.

References · 32

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2017Mask R-CNNcited by 7,259
  5. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  6. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  7. 2019Deep High-Resolution Representation Learning for Human Pose Estimationcited by 1,339
  8. 2019Objects as Pointscited by 1,172
  9. 2018OpenPose: Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,161
  10. 2016Realtime Multi-Person 2D Pose Estimation using Part Affinity Fieldscited by 1,061
  11. 2016Stacked Hourglass Networks for Human Pose Estimationcited by 913
  12. 2018Simple Baselines for Human Pose Estimation and Trackingcited by 502
20 more
  1. 2019PointRend: Image Segmentation as Renderingcited by 439
  2. 2017Deep Layer Aggregationcited by 436
  3. 2017Cascaded Pyramid Network for Multi-Person Pose Estimationcited by 341
  4. 2016RMPE: Regional Multi-person Pose Estimationcited by 340
  5. 2016Convolutional Pose Machinescited by 325
  6. 2019RepPoints: Point Set Representation for Object Detectioncited by 264
  7. 2019HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimationcited by 247
  8. 2018CrowdPose: Efficient Crowded Scenes Pose Estimation and A New Benchmarkcited by 214
  9. 2016Associative Embedding: End-to-End Learning for Joint Detection and Groupingcited by 211
  10. 2017Towards Accurate Multi-person Pose Estimation in the Wildcited by 131
  11. 2015DeepCut: Joint Subset Partition and Labeling for Multi Person Pose Estimationcited by 117
  12. 2016DeeperCut: A Deeper, Stronger, and Faster Multi-Person Pose Estimation Modelcited by 96
  13. 2019Single-Stage Multi-Person Pose Machinescited by 95
  14. 2020Learning Delicate Local Representations for Multi-Person Pose Estimationcited by 65
  15. 2020Point-Set Anchors for Object Detection, Instance Segmentation and Pose Estimationcited by 57
  16. 2018MultiPoseNet: Fast Multi-Person Pose Estimation using Pose Residual Networkcited by 47
  17. 2020BorderDet: Border Feature for Dense Object Detectioncited by 39
  18. 2016Multi-Person Pose Estimation with Local Joint-to-Person Associationscited by 18
  19. 2013Beyond Physical Connections: Tree Models in Human Pose Estimationcited by 14
  20. 2016Multi-Class Multi-Object Tracking using Changing Point Detectioncited by 2

Built on by

Not cited yet.